Paper: Biomedical Event Extraction by Multi-class Classification of Pairs of Text Entities

ACL ID W13-2006
Title Biomedical Event Extraction by Multi-class Classification of Pairs of Text Entities
Venue Proceedings of the BioNLP Shared Task 2013 Workshop
Session
Year 2013
Authors

This paper describes the HDS4NLP en- try to the BioNLP 2013 shared task on biomedical event extraction. This system is based on a pairwise model that trans- forms trigger classification in a simple multi-class problem in place of the usual multi-label problem. This model facili- tates inference compared to global models while relying on richer information com- pared to usual pipeline approaches. The HDS4NLP system ranked 6th on the Ge- nia task (43.03% f-score), and after fix- ing a bug discovered after the final submis- sion, it outperforms the winner of this task (with a f-score of 51.15%).